University of Oulu

Abidine, B.M., Fergani, L., Fergani, B. et al. The joint use of sequence features combination and modified weighted SVM for improving daily activity recognition. Pattern Anal Applic 21, 119–138 (2018).

The joint use of sequence features combination and modified weighted SVM for improving daily activity recognition

Saved in:
Author: Abidine, Bilal M’hamed1; Fergani, Lamya1; Fergani, Belkacem1;
Organizations: 1Laboratoire d'Ingénierie des Systèmes Intelligents et Communicants, LISIC Lab., Electronics and Computer Sciences Dept., University of Science and Technology Houari Boumediene (USTHB), 32, El Alia, Bab Ezzouar, 16111 Algiers, Algeria
2University of Birmingham, Electrical and Computer Engineering Dept., Birmingham, UK
3University of Oulu, Centre for Ubiquitous Computing, Oulu 90014, Finland
Format: article
Version: accepted version
Access: open
Online Access: PDF Full Text (PDF, 1.9 MB)
Persistent link:
Language: English
Published: Springer Nature, 2018
Publish Date: 2020-04-22


Two serious problems affecting the implementation of human activity recognition algorithms have been acknowledged. The first one corresponds to non-informative sequence features. The second is the class imbalance in the training data due to the fact that people do not spend the same amount of time on the different activities. To address these issues, we propose a new scheme based on a combination of principal component analysis, linear discriminant analysis (LDA) and the modified weighted support vector machines. First we added the most significant principal components to the set of features extracted using LDA. This work shows that a suitable sequence feature set combined with the modified WSVM based on our criterion classifier achieves good improvement and efficiency over the traditional used methods.

see all

Series: Pattern analysis and applications
ISSN: 1433-7541
ISSN-E: 1433-755X
ISSN-L: 1433-7541
Volume: 21
Issue: 1
Pages: 119 - 138
DOI: 10.1007/s10044-016-0570-y
Type of Publication: A1 Journal article – refereed
Field of Science: 113 Computer and information sciences
Copyright information: © Springer-Verlag London 2016. This is a post-peer-review, pre-copyedit version of an article published in Pattern Analysis and Applications. The final authenticated version is available online at: